| Commit message (Collapse) | Author | Age | Files | Lines |
| |
|
|
|
|
| |
Patch by Pranav Bhandarkar.
llvm-svn: 279998
|
| |
|
|
|
|
| |
Should have been done with r276646.
llvm-svn: 279996
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
GCNSchedStrategy re-uses most of GenericScheduler, it's just uses
a different method to compute the excess and critical register
pressure limits.
It's not enabled by default, to enable it you need to pass -misched=gcn
to llc.
Shader DB stats:
32464 shaders in 17874 tests
Totals:
SGPRS: 1542846 -> 1643125 (6.50 %)
VGPRS: 1005595 -> 904653 (-10.04 %)
Spilled SGPRs: 29929 -> 27745 (-7.30 %)
Spilled VGPRs: 334 -> 352 (5.39 %)
Scratch VGPRs: 1612 -> 1624 (0.74 %) dwords per thread
Code Size: 36688188 -> 37034900 (0.95 %) bytes
LDS: 1913 -> 1913 (0.00 %) blocks
Max Waves: 254101 -> 265125 (4.34 %)
Wait states: 0 -> 0 (0.00 %)
Totals from affected shaders:
SGPRS: 1338220 -> 1438499 (7.49 %)
VGPRS: 886221 -> 785279 (-11.39 %)
Spilled SGPRs: 29869 -> 27685 (-7.31 %)
Spilled VGPRs: 334 -> 352 (5.39 %)
Scratch VGPRs: 1612 -> 1624 (0.74 %) dwords per thread
Code Size: 34315716 -> 34662428 (1.01 %) bytes
LDS: 1551 -> 1551 (0.00 %) blocks
Max Waves: 188127 -> 199151 (5.86 %)
Wait states: 0 -> 0 (0.00 %)
Reviewers: arsenm, mareko, nhaehnle, MatzeB, atrick
Subscribers: arsenm, kzhuravl, llvm-commits
Differential Revision: https://reviews.llvm.org/D23688
llvm-svn: 279995
|
| |
|
|
|
|
|
|
|
|
| |
Reviewers: eugenis
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D23968
llvm-svn: 279993
|
| |
|
|
|
|
| |
std::queue was doing far to many heap allocations to be healthy.
llvm-svn: 279992
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
The SILoadStoreOptimizer can now look ahead more then one instruction when
looking for instructions to merge, which greatly improves the number of
loads/stores that we are able to merge.
Moving the pass before scheduling avoids increasing register pressure after
the scheduler, so that the scheduler's register pressure estimates will be
more accurate. It also gives more consistent results, since it is no longer
affected by minor scheduling changes.
Reviewers: arsenm
Subscribers: arsenm, kzhuravl, llvm-commits
Differential Revision: https://reviews.llvm.org/D23814
llvm-svn: 279991
|
| |
|
|
| |
llvm-svn: 279990
|
| |
|
|
| |
llvm-svn: 279988
|
| |
|
|
|
|
|
| |
There should be no functional change here, I'm just making the implementation
of "frem" (to libcall) legalization easier for a followup.
llvm-svn: 279987
|
| |
|
|
|
|
| |
Fixes bug 29289
llvm-svn: 279986
|
| |
|
|
|
|
|
|
|
|
|
|
| |
This bug shows up with diamonds that share unpredicable, unanalyzable branches.
There's an included test case from Hexagon. What was happening was that we were
attempting to predicate the branch instruction despite the fact that it was
checked to be the same. Now for unanalyzable branches we skip over the branch
instructions when predicating the block.
Differential Revision: https://reviews.llvm.org/D23939
llvm-svn: 279985
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
Calling __asan_poison_stack_memory and __asan_unpoison_stack_memory for small
variables is too expensive.
Code is disabled by default and can be enabled by -asan-experimental-poisoning.
PR27453
Reviewers: eugenis
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D23947
llvm-svn: 279984
|
| |
|
|
|
|
|
|
|
|
|
|
| |
Summary: No functional changes, just refactoring to make D23947 simpler.
Reviewers: eugenis
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D23954
llvm-svn: 279982
|
| |
|
|
|
|
|
|
|
| |
We forgot to remove optimization metadata when performing hosting during
FoldTwoEntryPHINode.
This fixes PR29163.
llvm-svn: 279980
|
| |
|
|
|
|
| |
We should revert this change once we drop support for MSVC 2013.
llvm-svn: 279979
|
| |
|
|
|
|
|
|
|
|
|
|
| |
With r279911 I accidentally regressed the gold/X86/start-lib-common.ll
test for newer golds (v1.12+) that honor the --start-lib/--end-lib.
Remove the alignment which should not be there to make this work with
both old and new gold linkers.
Additionally, now that we have a subdirectory for v1.12+ gold tests,
copy this test there and check specifically for the v1.12+ behavior.
llvm-svn: 279977
|
| |
|
|
|
|
| |
Further refine the model for loads.
llvm-svn: 279976
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
While walking the use chain for identifying rematerializable values in RS4GC,
add the case where the current value and base value are the same PHI nodes.
This will aid rematerialization of geps and casts instead of relocating.
Reviewers: sanjoy, reames, igor
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D23920
llvm-svn: 279975
|
| |
|
|
|
|
| |
Remove some debugging output to stderr that snuck in with r279576.
llvm-svn: 279974
|
| |
|
|
|
|
|
|
|
|
|
| |
Assuming the default FP env, we should not treat fdiv and frem any differently in terms of
trapping behavior than any other FP op. Ie, FP ops do not trap with the default FP env.
This matches how we treat the fdiv/frem in IR with isSafeToSpeculativelyExecute() and in
the backend after:
https://reviews.llvm.org/rL279970
llvm-svn: 279973
|
| |
|
|
|
|
|
| |
The fdiv test shows a problem similar to:
https://reviews.llvm.org/rL279970
llvm-svn: 279972
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
[Coroutines] Part 9: Add cleanup subfunction.
This patch completes coroutine heap allocation elision. Now, the heap elision example from docs\Coroutines.rst compiles and produces expected result (see test/Transform/Coroutines/ex3.ll)
Intrinsic Changes:
* coro.free gets a token parameter tying it to coro.id to allow reliably discovering all coro.frees associated with a particular coroutine.
* coro.id gets an extra parameter that points back to a coroutine function. This allows to check whether a coro.id describes the enclosing function or it belongs to a different function that was later inlined.
CoroSplit now creates three subfunctions:
# f$resume - resume logic
# f$destroy - cleanup logic, followed by a deallocation code
# f$cleanup - just the cleanup code
CoroElide pass during devirtualization replaces coro.destroy with either f$destroy or f$cleanup depending whether heap elision is performed or not.
Other fixes, improvements:
* Fixed buglet in Shape::buildFrame that was not creating coro.save properly if coroutine has more than one suspend point.
* Switched to using variable width suspend index field (no longer limited to 32 bit index field can be as little as i1 or as large as i<whatever-size_t-is>)
Reviewers: majnemer
Subscribers: llvm-commits, mehdi_amini
Differential Revision: https://reviews.llvm.org/D23844
llvm-svn: 279971
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Assuming the default FP env, we should not treat fdiv and frem any differently in terms of
trapping behavior than any other FP op. Ie, FP ops do not trap with the default FP env.
This matches how we treat these ops in IR with isSafeToSpeculativelyExecute(). There's a
similar bug in Constant::canTrap().
This bug manifests in PR29114:
https://llvm.org/bugs/show_bug.cgi?id=29114
...as a sequence of scalar divisions instead of a vector division on x86 for a <3 x float>
type.
Differential Revision: https://reviews.llvm.org/D23974
llvm-svn: 279970
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
MRI::getMaxLaneMaskForVReg does not always cover the whole register.
For example, on X86 the upper 16 bits of EAX cannot be accessed via
any subregister. Consequently, there is no lane mask that only covers
that part of EAX. The getMaxLaneMaskForVReg will return the union of
the lane masks for all subregisters, and in case of EAX, that union
will not cover the upper 16 bits.
This fixes https://llvm.org/bugs/show_bug.cgi?id=29132
llvm-svn: 279969
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
For shrinking SOPK instructions, we were creating a hint to tell the
register allocator to use the register allocated for src0 for the dst
operand as well. However, this seems to not work sometimes depending
on the order virtual registers are assigned physical registers.
To fix this, I've added a second allocation hint which does the reverse,
asks that the register allocated for dst is used for src0.
Reviewers: arsenm
Subscribers: arsenm, llvm-commits, kzhuravl
Differential Revision: https://reviews.llvm.org/D23862
llvm-svn: 279968
|
| |
|
|
| |
llvm-svn: 279967
|
| |
|
|
|
|
|
| |
There is no lit feature 'X86' so this test is just disabled completely.
Make it XFAIL until a solution is found.
llvm-svn: 279966
|
| |
|
|
|
|
| |
MC itself never needs to know about these sections.
llvm-svn: 279965
|
| |
|
|
|
|
|
|
|
|
|
|
| |
Summary: A follow-up fix on r279958.
Reviewers: bkramer
Subscribers: cfe-commits
Differential Revision: https://reviews.llvm.org/D23989
llvm-svn: 279964
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
The SILoadStoreOptimizer will need to use AliasAnalysis here in order to
move it before scheduling.
Reviewers: arsenm
Subscribers: arsenm, llvm-commits, kzhuravl
Differential Revision: https://reviews.llvm.org/D23813
llvm-svn: 279963
|
| |
|
|
|
|
|
|
|
| |
The problem occurs when the Node doesn't updated in place , UpdateNodeOperation() return the node that already exist.
In this case assert fail in PromoteIntegerOperand() , N have 2 results ( val + chain).
Differential Revision: http://reviews.llvm.org/D23756
llvm-svn: 279961
|
| |
|
|
|
|
|
|
| |
TEST sequence.
Differential Revision: http://reviews.llvm.org/D23490
llvm-svn: 279960
|
| |
|
|
|
|
|
|
|
|
|
|
| |
Summary: A follow-up fixing on http://llvm.org/viewvc/llvm-project?view=revision&revision=279905.
Reviewers: bkramer
Subscribers: cfe-commits
Differential Revision: https://reviews.llvm.org/D23985
llvm-svn: 279959
|
| |
|
|
|
|
|
|
| |
create a ConstantFPSDNode and let that be lowered.
This allows broadcast loads to used when available.
llvm-svn: 279958
|
| |
|
|
|
|
| |
integer operations when DQI isn't supported. This is consistent with the recent changes to promote logical operations to i64 vectors.
llvm-svn: 279957
|
| |
|
|
| |
llvm-svn: 279956
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
switch to using one indirect stub manager per logical dylib rather than one per
input module.
LogicalDylib is a helper class used by the CompileOnDemandLayer to manage
symbol resolution between modules during lazy compilation. In particular, it
ensures that internal symbols resolve correctly even in the case where multiple
input modules contain the same internal symbol name (which must to be promoted
to external hidden linkage so that functions in any given module can be split
out by lazy compilation). LogicalDylib's resolution scheme (before this commit)
required one stub-manager per input module. This made recompilation of functions
(by adding a module containing a new definition) difficult, as the stub manager
for any given symbol was bound to the module that supplied the original
definition. By using one stubs manager for the whole logical dylib symbols can
be more easily replaced, although support for doing this is not included in this
patch (it will be implemented in a follow up).
llvm-svn: 279952
|
| |
|
|
| |
llvm-svn: 279951
|
| |
|
|
| |
llvm-svn: 279950
|
| |
|
|
|
|
| |
Will be fixed in a future commit.
llvm-svn: 279949
|
| |
|
|
| |
llvm-svn: 279943
|
| |
|
|
| |
llvm-svn: 279939
|
| |
|
|
|
|
| |
constant vectors
llvm-svn: 279937
|
| |
|
|
|
|
|
|
|
|
| |
number of vector elements
Over eager combing prevents the correct folding of writemasks.
At the moment this occurs for ALL EVEX shuffles, in the future we need to check that the user of the root shuffle is a VSELECT that can fold to a writemask.
llvm-svn: 279934
|
| |
|
|
|
|
| |
Implement lowering for atomicrmw min/max/umin/umax. Fixes PR28818.
llvm-svn: 279933
|
| |
|
|
|
|
|
|
|
| |
Fixed a bug in run-time checks for possible memory conflicts inside loop.
The bug is in Low <-> High boundaries calculation. The High boundary should be calculated as "last memory access pointer + element size".
Differential revision: https://reviews.llvm.org/D23176
llvm-svn: 279930
|
| |
|
|
|
|
|
|
|
|
| |
AVX512F/AVX512VL.
Previously we weren't creating masked logical operations if bitcasts appeared between the logic operation and the select. The IR optimizers can move bitcasts across logic operations and create these cases. To minimize the number of cases we need to handle, this change promotes all logic ops to an i64 vector type just like when only SSE or AVX is available.
Unfortunately, this also has the consequence of making it difficult to select unmasked VPANDD/VPORD/VPXORD in all the cases it was previously used. This is the cause of most of the test change. This shouldn't result in any functional change though.
llvm-svn: 279929
|
| |
|
|
|
|
|
|
| |
are bitcasts between the logic op and the select.
This is taken from optimized IR of clang test cases for masked logic ops.
llvm-svn: 279928
|
| |
|
|
|
|
| |
instructions instead of ending 128/256. NFC
llvm-svn: 279927
|
| |
|
|
|
|
|
|
| |
Fix and improve tests
Differential Revision: https://reviews.llvm.org/D23899
llvm-svn: 279925
|